Probabilistic Guarantees for Safe Deep Reinforcement Learning

05/14/2020
by   Edoardo Bacci, et al.
0

Deep reinforcement learning has been successfully applied to many control tasks, but the application of such agents in safety-critical scenarios has been limited due to safety concerns. Rigorous testing of these controllers is challenging, particularly when they operate in probabilistic environments due to, for example, hardware faults or noisy sensors. We propose MOSAIC, an algorithm for measuring the safety of deep reinforcement learning agents in stochastic settings. Our approach is based on the iterative construction of a formal abstraction of a controller's execution in an environment, and leverages probabilistic model checking of Markov decision processes to produce probabilistic guarantees on safe behaviour over a finite time horizon. It produces bounds on the probability of safe operation of the controller for different initial configurations and identifies regions where correct behaviour can be guaranteed. We implement and evaluate our approach on agents trained for several benchmark control problems.

READ FULL TEXT
POST COMMENT

Comments

There are no comments yet.

Authors

page 1

page 2

page 3

page 4

01/10/2022

Verified Probabilistic Policies for Deep Reinforcement Learning

Deep reinforcement learning is an increasingly popular technique for syn...
02/02/2021

An Abstraction-based Method to Check Multi-Agent Deep Reinforcement-Learning Behaviors

Multi-agent reinforcement learning (RL) often struggles to ensure the sa...
02/24/2021

Towards Safe Continuing Task Reinforcement Learning

Safety is a critical feature of controller design for physical systems. ...
11/08/2021

On Assessing The Safety of Reinforcement Learning algorithms Using Formal Methods

The increasing adoption of Reinforcement Learning in safety-critical sys...
06/21/2019

Verification and Control of Turn-Based Probabilistic Real-Time Games

Quantitative verification techniques have been developed for the formal ...
10/06/2021

Adaptive control of a mechatronic system using constrained residual reinforcement learning

We propose a simple, practical and intuitive approach to improve the per...
05/25/2020

Formal Methods with a Touch of Magic

Machine learning and formal methods have complimentary benefits and draw...
This week in AI

Get the week's most popular data science and artificial intelligence research sent straight to your inbox every Saturday.